Vremenski raspon analize

## [1] "2024-03-14 UTC" "2024-06-10 UTC"

Broj postova

## [1] 11503

Deskriptiva na dnevnoj razini

## # A tibble: 1 × 7
##     min   max  mean    q1 median    q3    sd
##   <dbl> <dbl> <dbl> <dbl>  <dbl> <dbl> <dbl>
## 1     7   913  134.    73   100.  147.  125.

Broj objava po danima

Broj objava po izvoru/thread

Text analysis

Najčešće riječi (title)

Word frequency (txt)

Sentiment kroz vrijeme

Doprinos riječi sentimentu (crosentilex)

##### Doprinos riječi sentimentu (NRC)

Doprinos riječi raznom sentimentu (NRC)

Oblak riječi sa sentimentom CroSentilex

Oblak riječi sa sentimentom NRC

Profili po pozitivnosti i negativnosti

Najčešće fraze (bigrami; moguće i za 3 ili više riječi) (title)

Najčešće fraze (bigrami; moguće i za 3 ili više riječi)(txt)

## [1] "Most Frequent Co-occurrences:"
## [1] "Most Correlated Words:"

# Count word occurrences by date
word_counts_time <- tidy_text %>%
  count(date, word) %>%
  complete(date, word, fill = list(n = 0)) # Fill missing dates with zeroes

# Calculate time correlation of word frequencies
time_correlations <- word_counts_time %>%
  pairwise_cor(word, date, n, sort = TRUE)

# Display time correlations
print("Time Correlations between Target Words:")
print(time_correlations)

# Optional: Plot time trends of words
word_counts_time %>%
  ggplot(aes(x = date, y = n, color = word)) +
  geom_line() +
  labs(title = "Word Frequency Over Time", x = "Date", y = "Frequency") +
  theme_minimal()